Physical Sciences and Mathematics Commons^™

Adaptable And Trustworthy Machine Learning For Human Activity Recognition From Bioelectric Signals, Morgan S. Stuart

Theses and Dissertations

Enabling machines to learn measures of human activity from bioelectric signals has many applications in human-machine interaction and healthcare. However, labeled activity recognition datasets are costly to collect and highly varied, which challenges machine learning techniques that rely on large datasets. Furthermore, activity recognition in practice needs to account for user trust - models are motivated to enable interpretability, usability, and information privacy. The objective of this dissertation is to improve adaptability and trustworthiness of machine learning models for human activity recognition from bioelectric signals. We improve adaptability by developing pretraining techniques that initialize models for later specialization to unseen …

Defining Safe Training Datasets For Machine Learning Models Using Ontologies, Lynn C. Vonder Haar

Doctoral Dissertations and Master's Theses

Machine Learning (ML) models have been gaining popularity in recent years in a wide variety of domains, including safety-critical domains. While ML models have shown high accuracy in their predictions, they are still considered black boxes, meaning that developers and users do not know how the models make their decisions. While this is simply a nuisance in some domains, in safetycritical domains, this makes ML models difficult to trust. To fully utilize ML models in safetycritical domains, there needs to be a method to improve trust in their safety and accuracy without human experts checking each decision. This research proposes …

An Empirical Study Of Pre-Trained Model Reuse In The Hugging Face Deep Learning Model Registry, Wenxin Jiang, Nicholas Synovic, Matt Hyatt, Taylor R. Schorlemmer, Rohan Sethi, Yung-Hsiang Lu, George K. Thiruvathukal, James C. Davis

Department of Electrical and Computer Engineering Faculty Publications

Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of traditional software engineering, machine learning engineers have begun to reuse large-scale pre-trained models (PTMs) and fine-tune these models for downstream tasks. Prior works have studied reuse practices for traditional software packages to guide software engineers towards better package maintenance and dependency management. We lack a similar foundation of knowledge to guide behaviors in pre-trained model ecosystems.

In this work, we present the first empirical investigation of PTM reuse. …

Modeling And Analysis Of Trust Attack Based On Object-Oriented Petri Net, Guangqiu Huang, Bai Lu

Journal of System Simulation

Abstract: On the basis of trust attack graph, the object-oriented trust attack Petri net model was put forward, the dynamic model described the attack behaviors among components of trust entity object. By introducing the object Petri net, the trust attack relations between trust entity objects and components were shown in the Petri net, simulating the collaborative work between the components. According to the new trust relation reconstruction rules, a trust attack path inference algorithm was proposed to make the attacker knowing the changes of harmfulness when attacking the components, thus the attacker could decide the attack direction. The maximal …

An Empirical Investigation Of The Willingness Of Us Intelligence Community Analysts To Contribute Knowledge To A Knowledge Management System (Kms) In A Highly Classified And Sensitive Environment, Robert Hambly

CCE Theses and Dissertations

Since September 11, 2001, the United States Government (USG) has possessed unparalleled capability in terms of dedicated intelligence and information collection assets supporting the analysts of the Intelligence Community (IC). The USG IC has sponsored, developed, and borne witness to extraordinary advances in technology, techniques, and procedures focused on knowledge harvesting, knowledge sharing, and collaboration. Knowledge, within successful (effective & productive) organizations, exists as a commodity; a commodity that can be created, captured, imparted, shared, and leveraged. The research problem that this study addressed is the challenge of maintaining strong organizational effectiveness and productivity through the use of an information …

Towards A Conceptual Model Of User Acceptance Of Location-Based Emergency Services, Anas Aloudat, Katina Michael

Professor Katina Michael

This paper investigates the introduction of location-based services by government as part of an all-hazards approach to modern emergency management solutions. Its main contribution is in exploring the determinants of an individual’s acceptance or rejection of location services. The authors put forward a conceptual model to better predict why an individual would accept or reject such services, especially with respect to emergencies. While it may be posited by government agencies that individuals would unanimously wish to accept life-saving and life-sustaining location services for their well-being, this view remains untested. The theorised determinants include: visibility of the service solution, perceived service …

Common Criteria Meets Realpolitik Trust, Alliances, And Potential Betrayal, Jan Kallberg

Jan Kallberg

Common Criteria for Information Technology Security Evaluation has the ambition to be a global standard for IT-security certification. The issued certifications are mutually recognized between the signatories of the Common Criteria Recognition Arrangement. The key element in any form of mutual relationships is trust. A question raised in this paper is how far trust can be maintained in Common Criteria when additional signatories enter with conflicting geopolitical interests to earlier signatories. Other issues raised are control over production, the lack of permanent organization in the Common Criteria, which leads to concerns of being able to oversee the actual compliance. As …

Location-Based Social Networking And Its Impact On Trust In Relationships, Sarah Jean Fusco, Roba Abbas, Katina Michael, Anas Aloudat

Professor Katina Michael

Location based social networking (LBSN) applications are part of a new suite of social networking tools. LBSN is the convergence between location based services (LBS) and online social networking (OSN). LBSN applications offer users the ability to look up the location of another “friend” remotely using a smart phone, desktop or other device, anytime and anywhere. Users invite their friends to participate in LBSN and there is a process of consent that follows. This paper explores the potential impact of LBSN upon trust in society. It looks at the willingness of individuals to share their location data with family, friends, …

Cloud Computing:Strategies For Cloud Computing Adoption, Faith Shimba

Dissertations

The advent of cloud computing in recent years has sparked an interest from different organisations, institutions and users to take advantage of web applications. This is a result of the new economic model for the Information Technology (IT) department that cloud computing promises. The model promises a shift from an organisation required to invest heavily for limited IT resources that are internally managed, to a model where the organisation can buy or rent resources that are managed by a cloud provider, and pay per use. Cloud computing also promises scalability of resources and on-demand availability of resources.

Although, the adoption …

Trust, Collaboration, And Financial Return In Conservation/Development Partnerships, New England Environmental Finance Center

Economics and Finance

In early 2002 the New England Environmental Finance Center hosted a series of roundtable discussions among municipal officials, residential developers, land trust representatives, and others about "Innovative Approaches to Land Conservation and Smart Growth". Among our observations was that for many of the over 20 conservation/development partnerships we discussed in the series, creation and maintenance of trust was central to success or failure of various stages of the partnership. This suggested a link between creation of trust and financial return for traditionally opposed project partners.

To further examine this matter, we interviewed 11 round table participants and asked questions about …

Lands Available For Mineral Leasing, John R. Little, Jr.

Public Lands Mineral Leasing: Issues and Directions (Summer Conference, June 10-11)

14 pages.

Contains references.